Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis

19 Aug 2019Zongwei ZhouVatsal SodhaMd Mahfuzur Rahman SiddiqueeRuibin FengNima TajbakhshMichael B. GotwayJianming Liang

Transfer learning from natural image to medical image has established as one of the most practical paradigms in deep learning for medical image analysis. However, to fit this paradigm, 3D imaging tasks in the most prominent imaging modalities (e.g., CT and MRI) have to be reformulated and solved in 2D, losing rich 3D anatomical information and inevitably compromising the performance... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Brain Tumor Segmentation BRATS-2013 ModelGenesis Dice Score 0.9258 # 1
Lung Nodule Segmentation LIDC-IDRI ModelGenesis IoU 77.62 # 1
Lung Nodule Segmentation LIDC-IDRI ModelGenesis Dice 75.86 # 1
Liver Segmentation LiTS2017 ModelGenesis IoU 79.52 # 1
Liver Segmentation LiTS2017 ModelGenesis Dice 91.13 # 1
Lung Nodule Detection LUNA2016 FPRED ModelGenesis AUC 98.20 # 1
Pulmonary Embolism Detection PE-CAD FPRED ModelGenesis AUC 88.04 # 1